{"ID":2891010,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18580","arxiv_id":"2507.18580","title":"System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition","abstract":"This paper presents our system for CCL25-Eval Task 10, addressing Fine-Grained Chinese Hate Speech Recognition (FGCHSR). We propose a novel SRAG-MAV framework that synergistically integrates task reformulation(TR), Self-Retrieval-Augmented Generation (SRAG), and Multi-Round Accumulative Voting (MAV). Our method reformulates the quadruplet extraction task into triplet extraction, uses dynamic retrieval from the training set to create contextual prompts, and applies multi-round inference with voting to improve output stability and performance. Our system, based on the Qwen2.5-7B model, achieves a Hard Score of 26.66, a Soft Score of 48.35, and an Average Score of 37.505 on the STATE ToxiCN dataset, significantly outperforming baselines such as GPT-4o (Average Score 15.63) and fine-tuned Qwen2.5-7B (Average Score 35.365). The code is available at https://github.com/king-wang123/CCL25-SRAG-MAV.","short_abstract":"This paper presents our system for CCL25-Eval Task 10, addressing Fine-Grained Chinese Hate Speech Recognition (FGCHSR). We propose a novel SRAG-MAV framework that synergistically integrates task reformulation(TR), Self-Retrieval-Augmented Generation (SRAG), and Multi-Round Accumulative Voting (MAV). Our method reformu...","url_abs":"https://arxiv.org/abs/2507.18580","url_pdf":"https://arxiv.org/pdf/2507.18580v1","authors":"[\"Jiahao Wang\",\"Ramen Liu\",\"Longhui Zhang\",\"Jing Li\"]","published":"2025-07-24T16:56:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":611838,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891010,"paper_url":"https://arxiv.org/abs/2507.18580","paper_title":"System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition","repo_url":"https://github.com/king-wang123/CCL25-SRAG-MAV","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}